Conformer model for long-form audio (minutes to hours)
40 languages · benchmarked
Google Latest (Long) is a speech-to-text model from Google Cloud. In our standardized benchmarks it reaches 22.55% word error rate, ranking #30 of 35 models tested. It supports 40 languages and runs at $0.011/min — a premium option.
Its nearest benchmarked alternative is Soniox STT (Async). Best suited for multilingual workloads.
Overall Score
38.7
#30 of 35
Word Error Rate
22.55%
Character Error Rate
13.81%
Match Error Rate
22.18%
Word Info Lost
29.95%
Avg Latency
13.2s
Benchmarks Run
34
last 30 runs
Word error rate
22.55%
↓ 18.0% · 30d
3 runs ago
latest
Avg latency
13.2s
↓ 2.1% · 30d
3 runs ago
latest
overall WER · 35 models
Google Latest (Long)
field · 34 models
lower-left is better
8 categories
WER
lower is better
Legal
6.4%
Medical
6.9%
Conversational
10.0%
Technical
10.7%
Finance
11.7%
General
18.0%
Noisy Environment
48.5%
Code-Switching
78.7%
| Category | WER | CER | MER | WIL | Latency | Benchmarks |
|---|---|---|---|---|---|---|
Code-Switching | 78.69% | 60.26% | 76.73% | 87.43% | 24.8s | 2 |
Conversational | 9.99% | 5.84% | 9.90% | 14.51% | 14.5s | 2 |
Finance | 11.71% | 5.68% | 11.54% | 18.55% | 16.8s | 2 |
General | 17.99% | 10.10% | 17.69% | 26.10% | 12.5s | 18 |
Legal | 6.38% | 4.12% | 6.31% | 8.62% | 17.1s | 2 |
Medical | 6.94% | 3.10% | 6.89% | 10.89% | 12.0s | 2 |
Noisy Environment | 48.53% | 29.55% | 47.98% | 59.02% | 6.3s | 4 |
Technical | 10.66% | 5.77% | 10.51% | 16.13% | 14.2s | 2 |
5 accents
| Accent | WER | Benchmarks |
|---|---|---|
African | 27.69% | 1 |
Australian | 38.46% | 1 |
Indian | 58.73% | 1 |
British | 13.43% | 1 |
American | 47.17% | 1 |
Rate
$0.0107
/min
Per-second billing. Bring your own provider key and pay your provider directly — a 5% routing fee applies (first 100 min/mo free).
Set up BYOKCost estimator
1 hour
$0.64
10 hours
$6.41
100 hours
$64.08
1,000 hours
$640.80
Billed per second of audio processed.
Model ID
google/latest-long
Authenticate every request with your secret API key as a Bearer token. Issue a key from your dashboard.
Use it with your agent
Paste this into Claude Code, Cursor, Codex or any agent with a shell. It installs the CLI and the OpenTranscription skill, then transcribes with this model.
Quickstart
Upload your audio, create a job with this model, then poll the job or set a webhook_url to be notified when it completes.
Key parameters
file_path
string
required
Storage path returned by the upload step.
model
string
required
The model to run this job on.
models
string[]
Ordered fallback chain: primary first, then backups tried in order if a provider fails.
language
string
ISO 639-1 language code. Omit to auto-detect.
word_timestamps
boolean
Per-word start, end and confidence. Defaults to true; send false to leave them out.
webhook_url
string
HTTPS URL notified with the result when the job completes. Delivered events are signed (X-OT-Signature).
title
string
Display name for this job in the dashboard. Falls back to the file name.
Response
A completed job returns the transcript in the OpenTranscription Unified Schema (OTUS).
Webhooks — skip polling
We POST a signed event to your webhook_url when a job completes or fails; verify the X-OT-Signature (HMAC-SHA256, reject if older than 300 s) and dedupe on the event id, then fetch the full transcript via GET /api/v1/transcriptions/{id}.
Rate-limited per tier — see the X-RateLimit-* response headers.
Full API referenceSupported Languages
Supported Formats
Features
Limits
Max file size
No documented limit
Max duration
8 h